The pavement maintenance and rehabilitation (M&R) strategy selection problem is an exceedingly hard problem to solve optimally. In this paper, a novel Adaptive Hybrid Genetic Algorithm (AHGA) is proposed which incorporates Local Search (LS) techniques into Genetic Algorithms (GA) to improve the overall efficiency and effectiveness of the search. Specifically, it contains two dynamic learning mechanisms to guide and combine the exploration and exploitation search processes adaptively. The first learning mechanism aims to assess the worthiness of conducting an LS reactively and to control the computational resources allocated to the application of this search technique efficiently. The second learning mechanism uses instantaneously learned probabilities to select from a set of pre-defined LS operators which compete against each other for selection which is the most appropriate at any particular stage of the search to take over from the evolutionary-based search process. The new AHGA is compared to a non-hybridized version of the GA by applying the algorithms to several case studies in order to determine the best pavement M&R strategy that minimizes the present value of the total M&R costs. The results show that the proposed AHGA statistically outperforms the traditional GA in terms of efficiency.